218 citations
- Huawei Technologies (China)CN15 papers
- The University of Texas at AustinUS7 papers
- Huawei Technologies (United Kingdom)GB6 papers
- Rutgers, The State University of New JerseyUS4 papers
- University of California, Santa CruzUS4 papers
- Futurewei Technologies (United States)US3 papers
- Chinese Academy of SciencesCN2 papers
- Cloud Computing CenterCN2 papers
- Qatar UniversityQA2 papers
- University at Albany, State University of New YorkUS2 papers
- University of DelawareUS2 papers
- University of Science and Technology of ChinaCN2 papers
57 papers
Accurate Simulation Pipeline for Passive Single-Photon Imaging
Aleksi Suonsivu, Lauri Salmela, Leevi Uosukainen +3
Single-Photon Avalanche Diodes (SPADs) are new and promising imaging sensors. These sensors are sensitive enough to detect individual photons hitting each pixel, with extreme tempo…
SAQ: Pushing the Limits of Vector Quantization through Code Adjustment and Dimension Segmentation
Hui Li, Shiyuan Deng, Xiao Yan +2
Approximate Nearest Neighbor Search (ANNS) plays a critical role in applications such as search engines, recommender systems, and RAG for LLMs. Vector quantization (VQ), a crucial…
AIstorian lets AI be a historian: A KG-powered multi-agent system for accurate biography generation
Fengyu Li, Yilin Li, Junhao Zhu +6
Huawei has always been committed to exploring the AI application in historical research. Biography generation, as a specialized form of abstractive summarization, plays a crucial r…
ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation
Shu Wang, Yixiang Fang, Yingli Zhou +2
Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models (LLMs) for solving question-answer (QA) tasks. The state-of-t…
Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding
Konstantin Berestizshevsky, Renzo Andri, Lukas Cavigelli
We present Top-Theta (Top-) Attention, a training-free method for sparsifying transformer attention during inference. Our key insight is that static, per-head thresholds can be…
Digital Forgetting in Large Language Models: A Survey of Unlearning Methods
Alberto Blanco-Justicia, Najeeb Jebreel, Benet Manzanares +4
The objective of digital forgetting is, given a model with undesirable knowledge or behavior, obtain a new model where the detected issues are no longer present. The motivations fo…